oliver-aizip commited on
Commit
e7fd2d9
·
1 Parent(s): dc2d37a

remove cogito for gpu-hour reasons and add approved llama models

Browse files
Files changed (1) hide show
  1. utils/models.py +3 -3
utils/models.py CHANGED
@@ -10,13 +10,13 @@ from .shared import generation_interrupt
10
  models = {
11
  "Qwen2.5-1.5b-Instruct": "qwen/qwen2.5-1.5b-instruct",
12
  "Qwen2.5-3b-Instruct": "qwen/qwen2.5-3b-instruct",
13
- #"Llama-3.2-1b-Instruct": "meta-llama/llama-3.2-1b-instruct",
14
- #"Llama-3.2-3b-Instruct": "meta-llama/llama-3.2-3b-instruct",
15
  "Gemma-3-1b-it": "google/gemma-3-1b-it",
16
  #"Gemma-3-4b-it": "google/gemma-3-4b-it",
17
  "Gemma-2-2b-it": "google/gemma-2-2b-it",
18
  "Phi-4-mini-instruct": "microsoft/phi-4-mini-instruct",
19
- "Cogito-v1-preview-llama-3b": "deepcogito/cogito-v1-preview-llama-3b",
20
  "IBM Granite-3.3-2b-instruct": "ibm-granite/granite-3.3-2b-instruct",
21
 
22
  }
 
10
  models = {
11
  "Qwen2.5-1.5b-Instruct": "qwen/qwen2.5-1.5b-instruct",
12
  "Qwen2.5-3b-Instruct": "qwen/qwen2.5-3b-instruct",
13
+ "Llama-3.2-1b-Instruct": "meta-llama/llama-3.2-1b-instruct",
14
+ "Llama-3.2-3b-Instruct": "meta-llama/llama-3.2-3b-instruct",
15
  "Gemma-3-1b-it": "google/gemma-3-1b-it",
16
  #"Gemma-3-4b-it": "google/gemma-3-4b-it",
17
  "Gemma-2-2b-it": "google/gemma-2-2b-it",
18
  "Phi-4-mini-instruct": "microsoft/phi-4-mini-instruct",
19
+ #"Cogito-v1-preview-llama-3b": "deepcogito/cogito-v1-preview-llama-3b",
20
  "IBM Granite-3.3-2b-instruct": "ibm-granite/granite-3.3-2b-instruct",
21
 
22
  }